Authenticating corrupted face image based on noise model

Ho Choul Jung; Bon Woo Hwang; Seong Whan Lee

doi:10.1109/AFGR.2004.1301543

Authenticating corrupted face image based on noise model

Ho Choul Jung^*
, Bon Woo Hwang
, Seong Whan Lee

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

32 Citations (Scopus)

Abstract

In this paper, we propose a method for authenticating corrupted face images based on noise model. The proposed method first generates corrupted images by controlling noise parameters in the training phase. The corrupted images and noise parameters are represented by a linear combination of prototypes of the corrupted images and the noise parameters. With the corrupted image and an original image, we can estimate noise parameters of the corrupted face image in the testing phase. Then, we can make a synthesized face image from the original face image with the estimated noise parameters and verify it with the corrupted face image. Our experimental results show that the proposed method can estimate noise parameters accurately and improve the performance of face authentication.

Original language	English
Title of host publication	Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004
Publisher	IEEE Computer Society
Pages	272-277
Number of pages	6
ISBN (Print)	0769521223, 9780769521220
DOIs	https://doi.org/10.1109/AFGR.2004.1301543
Publication status	Published - 2004
Event	Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004 - Seoul, Korea, Republic of Duration: 2004 May 17 → 2004 May 19

Publication series

Name	Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition

Other

Other	Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004
Country/Territory	Korea, Republic of
City	Seoul
Period	04/5/17 → 04/5/19

ASJC Scopus subject areas

General Engineering

Access to Document

10.1109/AFGR.2004.1301543

Cite this

Jung, H. C., Hwang, B. W., & Lee, S. W. (2004). Authenticating corrupted face image based on noise model. In Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004 (pp. 272-277). (Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition). IEEE Computer Society. https://doi.org/10.1109/AFGR.2004.1301543

Authenticating corrupted face image based on noise model. / Jung, Ho Choul; Hwang, Bon Woo; Lee, Seong Whan.
Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004. IEEE Computer Society, 2004. p. 272-277 (Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Jung, HC, Hwang, BW & Lee, SW 2004, Authenticating corrupted face image based on noise model. in Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004. Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition, IEEE Computer Society, pp. 272-277, Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004, Seoul, Korea, Republic of, 04/5/17. https://doi.org/10.1109/AFGR.2004.1301543

@inproceedings{44c16dd9337e4ac4a404b529a7cae11f,

title = "Authenticating corrupted face image based on noise model",

abstract = "In this paper, we propose a method for authenticating corrupted face images based on noise model. The proposed method first generates corrupted images by controlling noise parameters in the training phase. The corrupted images and noise parameters are represented by a linear combination of prototypes of the corrupted images and the noise parameters. With the corrupted image and an original image, we can estimate noise parameters of the corrupted face image in the testing phase. Then, we can make a synthesized face image from the original face image with the estimated noise parameters and verify it with the corrupted face image. Our experimental results show that the proposed method can estimate noise parameters accurately and improve the performance of face authentication.",

author = "Jung, \{Ho Choul\} and Hwang, \{Bon Woo\} and Lee, \{Seong Whan\}",

year = "2004",

doi = "10.1109/AFGR.2004.1301543",

language = "English",

isbn = "0769521223",

series = "Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition",

publisher = "IEEE Computer Society",

pages = "272--277",

booktitle = "Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004",

note = "Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004 ; Conference date: 17-05-2004 Through 19-05-2004",

}

TY - GEN

T1 - Authenticating corrupted face image based on noise model

AU - Jung, Ho Choul

AU - Hwang, Bon Woo

AU - Lee, Seong Whan

PY - 2004

Y1 - 2004

N2 - In this paper, we propose a method for authenticating corrupted face images based on noise model. The proposed method first generates corrupted images by controlling noise parameters in the training phase. The corrupted images and noise parameters are represented by a linear combination of prototypes of the corrupted images and the noise parameters. With the corrupted image and an original image, we can estimate noise parameters of the corrupted face image in the testing phase. Then, we can make a synthesized face image from the original face image with the estimated noise parameters and verify it with the corrupted face image. Our experimental results show that the proposed method can estimate noise parameters accurately and improve the performance of face authentication.

AB - In this paper, we propose a method for authenticating corrupted face images based on noise model. The proposed method first generates corrupted images by controlling noise parameters in the training phase. The corrupted images and noise parameters are represented by a linear combination of prototypes of the corrupted images and the noise parameters. With the corrupted image and an original image, we can estimate noise parameters of the corrupted face image in the testing phase. Then, we can make a synthesized face image from the original face image with the estimated noise parameters and verify it with the corrupted face image. Our experimental results show that the proposed method can estimate noise parameters accurately and improve the performance of face authentication.

UR - https://www.scopus.com/pages/publications/4544358488

U2 - 10.1109/AFGR.2004.1301543

DO - 10.1109/AFGR.2004.1301543

M3 - Conference contribution

AN - SCOPUS:4544358488

SN - 0769521223

SN - 9780769521220

T3 - Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition

SP - 272

EP - 277

BT - Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004

PB - IEEE Computer Society

T2 - Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004

Y2 - 17 May 2004 through 19 May 2004

ER -

Authenticating corrupted face image based on noise model

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this